research-plus
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill requires a background subagent to do “web fetches”/source sweeps and then to write/read findings as Markdown; that means runtime-fetched outsider web content and scraped text can be ingested into the subagent’s LLM context during research.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata